{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T15:36:51Z","timestamp":1770046611838,"version":"3.49.0"},"reference-count":21,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2021,9,15]]},"abstract":"<jats:p>Neural networks can approximate data because of owning many compact non-linear layers. In high-dimensional space, due to the curse of dimensionality, data distribution becomes sparse, causing that it is difficulty to provide sufficient information. Hence, the task becomes even harder if neural networks approximate data in high-dimensional space. To address this issue, according to the Lipschitz condition, the two deviations, i.e., the deviation of the neural networks trained using high-dimensional functions, and the deviation of high-dimensional functions approximation data, are derived. This purpose of doing this is to improve the ability of approximation high-dimensional space using neural networks. Experimental results show that the neural networks trained using high-dimensional functions outperforms that of using data in the capability of approximation data in high-dimensional space. We find that the neural networks trained using high-dimensional functions more suitable for high-dimensional space than that of using data, so that there is no need to retain sufficient data for neural networks training. Our findings suggests that in high-dimensional space, by tuning hidden layers of neural networks, this is hard to have substantial positive effects on improving precision of approximation data.<\/jats:p>","DOI":"10.3233\/jifs-211417","type":"journal-article","created":{"date-parts":[[2021,8,3]],"date-time":"2021-08-03T12:51:28Z","timestamp":1627995088000},"page":"3739-3750","source":"Crossref","is-referenced-by-count":3,"title":["Neural networks trained with high-dimensional functions approximation data in high-dimensional space"],"prefix":"10.1177","volume":"41","author":[{"given":"Jian","family":"Zheng","sequence":"first","affiliation":[{"name":"Chongqing Aerospace Polytechnic, Chongqing, China"}]},{"given":"Jianfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Chongqing Aerospace Polytechnic, Chongqing, China"}]},{"given":"Yanping","family":"Chen","sequence":"additional","affiliation":[{"name":"Chongqing Aerospace Polytechnic, Chongqing, China"}]},{"given":"Shuping","family":"Chen","sequence":"additional","affiliation":[{"name":"Chongqing Aerospace Polytechnic, Chongqing, China"}]},{"given":"Jingjin","family":"Chen","sequence":"additional","affiliation":[{"name":"Chongqing Aerospace Polytechnic, Chongqing, China"}]},{"given":"Wenlong","family":"Zhong","sequence":"additional","affiliation":[{"name":"Chongqing Aerospace Polytechnic, Chongqing, China"}]},{"given":"Wenling","family":"Wu","sequence":"additional","affiliation":[{"name":"Chongqing Aerospace Polytechnic, Chongqing, China"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-211417_ref1","first-page":"1","article-title":"Deep learning for universal linear embeddings of nonlinear dynamics[J]","volume":"9","author":"Bethany","year":"2018","journal-title":"Nature Communications"},{"key":"10.3233\/JIFS-211417_ref2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning [J]","volume":"521","author":"Le Cun","year":"2015","journal-title":"Nature"},{"key":"10.3233\/JIFS-211417_ref3","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.eswa.2016.10.065","article-title":"Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN [J]","volume":"72","author":"Chen","year":"2017","journal-title":"Expert Systems with Applications"},{"issue":"12","key":"10.3233\/JIFS-211417_ref4","doi-asserted-by":"crossref","first-page":"2486","DOI":"10.1109\/TNNLS.2015.2479223","article-title":"Deep learning of part-based representation of data using sparse autoencoders with nonnegativity constraints [J]","volume":"27","author":"Hosseini-Asl","year":"2016","journal-title":"IEEE Transactions on Neural Networks and Learning System"},{"issue":"8","key":"10.3233\/JIFS-211417_ref5","doi-asserted-by":"crossref","first-page":"2519","DOI":"10.1109\/TMTT.2016.2586055","article-title":"An artificial neural network-based electrothermal model for GaN HEMTs with dynamic trapping effects consideration [J]","volume":"64","author":"Huang","year":"2016","journal-title":"IEEE Transactions on Microwave Theory and Techniques"},{"key":"10.3233\/JIFS-211417_ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-018-04316-3","article-title":"Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science [J]","volume":"9","author":"Mocanu","year":"2018","journal-title":"Nature Communications"},{"issue":"12","key":"10.3233\/JIFS-211417_ref12","doi-asserted-by":"crossref","first-page":"5603","DOI":"10.1109\/TNNLS.2020.2975051","article-title":"A Universal Approximation Result for Difference of Log-Sum-Exp Neural Networks [J]","volume":"31","author":"Calafiore","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"7","key":"10.3233\/JIFS-211417_ref15","first-page":"641","article-title":"Principal component analysis [J]","volume":"14","author":"Lever","year":"2017","journal-title":"ethods"},{"key":"10.3233\/JIFS-211417_ref16","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1038\/s41592-019-0353-7","article-title":"Scalable analysis of cell-type composition from single-cell transcriptomics using deep recurrent learning [J]","volume":"16","author":"Deng","year":"2019","journal-title":"Nature Methods"},{"key":"10.3233\/JIFS-211417_ref17","first-page":"487","article-title":"Image reconstruction by domain transform manifold learning [J]","volume":"555","author":"Zhu","year":"2018","journal-title":"ature"},{"issue":"3","key":"10.3233\/JIFS-211417_ref18","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1109\/TNNLS.2013.2276044","article-title":"Function approximation using combined unsupervised and supervised learning [J]","volume":"25","author":"Andras","year":"2014","journal-title":"IEEE Transactions Neural Networks and Learning System"},{"key":"10.3233\/JIFS-211417_ref20","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.neunet.2017.12.007","article-title":"On the approximation by single hidden layer feedforward neural networks with fixed weights [J]","volume":"98","author":"Guliyev","year":"2018","journal-title":"Neural Networks"},{"issue":"1","key":"10.3233\/JIFS-211417_ref21","first-page":"1","article-title":"Efficient probabilistic inference in generic neural networks trained with non-probabilistic feedback","volume":"8","author":"Emin Orhan","year":"2017","journal-title":"Nature Communications"},{"key":"10.3233\/JIFS-211417_ref23","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1016\/j.neunet.2018.08.019","article-title":"Optimal approximation of piecewise smooth functions using deep ReLU neural networks [J]","volume":"108","author":"Petersen","year":"2018","journal-title":"Neural Networks"},{"issue":"01","key":"10.3233\/JIFS-211417_ref24","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1142\/S0219530518500203","article-title":"Deep learning in high dimension: Neural network expression rates for generalized polynomial chaos expansions in UQ [J]","volume":"17","author":"Schwab","year":"2019","journal-title":"Anal. Appl"},{"key":"10.3233\/JIFS-211417_ref27","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.neunet.2017.07.002","article-title":"Error bounds for approximations with deep ReLU networks [J]","volume":"94","author":"Yarotsky","year":"2017","journal-title":"Neural Networks"},{"issue":"4","key":"10.3233\/JIFS-211417_ref31","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1109\/TNNLS.2019.2919676","article-title":"Adaptive global sliding-mode control for dynamic systems using double hidden layer recurrent neural network structure [J]","volume":"31","author":"Chu","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"10.3233\/JIFS-211417_ref32","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1023\/A:1018966213079","article-title":"Generalization bounds for function approximation from scattered noisy data[J]","volume":"10","author":"Niyogi","year":"1999","journal-title":"Advances in Computational Mathematics"},{"issue":"3","key":"10.3233\/JIFS-211417_ref33","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1109\/18.256500","article-title":"Universal approximation bounds for superpositions of a sigmoidal function [J]","volume":"39","author":"Barron","year":"1993","journal-title":"IEEE Transactions on Information Theory"},{"key":"10.3233\/JIFS-211417_ref35","first-page":"1457","article-title":"Non-negative matrix factorization with sparseness constraints [J]","volume":"5","author":"Hoyer","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/JIFS-211417_ref36","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1007\/s10618-015-0444-8","article-title":"On the evaluation of unsupervised outlier detection: measures, datasets, and an empirical study [J]","volume":"30","author":"Campos","year":"2016","journal-title":"Data Mining & Knowledge Discovery"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-211417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T04:24:35Z","timestamp":1770006275000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-211417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,15]]},"references-count":21,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/jifs-211417","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,15]]}}}